Closed Jarrome closed 3 years ago
Hi @Jarrome,
This is a bit weird. People usually get slightly better accuracies than the paper. Could you please send the log as well as the environment to me (crane.h.fan@gmail.com)? It could be much better if you could also provide the log with 24 frames. I would like to repeat and check the problem.
Many thanks.
Best regards.
Hi, @hehefan,
Thanks for your quick reply. I have emailed you the repo and piplist. I will now try the 24 frames, and send you latter.
Best regards.
Hi @hehefan,
I also got a slightly lower accuracy 89.2 with 16 frames.
Hi @hehefan
I achieve a 92.68 with 24 frames. Great work.
Hi @vivonicole,
The accuracy of 89.2 with 16 frames is reasonable. Tuning the radius might improve the performance. Thank you.
Best regards.
I close this issue as the problem might be from the compiling of sampling&grouping layer. Not from the authors' work. It can be reopen, when there is any other find on the clustering step.
Hi @hehefan
I achieve a 92.68 with 24 frames. Great work.
Can you please confirm if this result is for PSTNet or PSTNet++?
I got 90.24 for PSTNet with 24 frames. Can you please share the logs?
Hi @hehefan I achieve a 92.68 with 24 frames. Great work.
Can you please confirm if this result is for PSTNet or PSTNet++?
I got 90.24 for PSTNet with 24 frames. Can you please share the logs?
I'm sure it was PSTNet but I did not save the log..
@hehefan
For 24 frames with a batch size of 24, using 4x2080Ti, I got 93.03% accuracy.
What could be the reason for so much fluctuation in accuracy despite setting a random seed for numpy and PyTorch?
Hi @sheshap,
The fluctuation may be caused by the small scale of the MSR-Action3D dataset and the data augmentation. The accuracy is usually around 91.9±1%.
Thank you for the reply.
In the case of MSR-Action3D, data augmentation is only scaling, right?
As per the datasets/msr.py file below lines: if self.train:
scales = np.random.uniform(0.9, 1.1, size=3)
clip = clip * scales
Thanks
Hi @sheshap,
You are right. But note that, because each frame has more than 2048 points. Sampling points is also a random source.
Best regards.
Great works! I've read it thoroughly and can easily run your code.
One issue is when I directly use the
train-msr
and finish train, the final acc is 84 and 83 for two repeat. I think they are with 16 frames. My repeats get lower scoring comparing to the paper.I think it might because there are some parameter change in the script. Would you be convenient to check out?